What should it check?
Start with the answer already in front of you and the original task. Ask AI to identify what is missing, unsupported, unclear, or poorly matched to what you needed. That gives it more to work with than a vague request to do better.
Which corrections matter?
Have it explain the weaknesses and revise the ones that affect the result. If it gives itself a score, focus on the reasons behind that score. A higher self-rating is not a substitute for a clearer, more accurate answer.
What can you verify?
Check material facts, numbers, sources, and conclusions against reliable evidence. AI can sound confident while being wrong, and asking whether it is certain does not fix that. Use the review to find where you need to look harder. Stop revising when the work meets your requirements, rather than collecting versions for their own sake.
Sources
Sources
- Jeff Fargo, Fargo Talks, “Do This Before You Trust AI”
- OpenAI Help Center: Does ChatGPT tell the truth?
- OpenAI: Graders
Transcript
Verbatim from the Fargo Walks clip, as recorded.
Don't be a lazy AI prompter. "Do better" is the laziest freaking thing you can tell AI. Challenge it. Ask it, "Is this the best you can do?" Are you giving me this with 100% confidence? Or a really good one is rigorously grade yourself and defend what you just gave me. Whatever task it is, then you're giving AI something to work with. I'm Jeff Fargo, and I could help streamline and scale your business with AI. Go forth.